OpenRouter LLM API pricing
Every model OpenRouter serves, with its pricing per 1M tokens and the exact model ID to copy. Sorted cheapest input first, with models OpenRouter lists no paid price for at the end. Listed prices from LiteLLM, OpenRouter and Vercel.
Models served
418
on this provider
Cheapest input
$0.01
per 1M tokens
Cheapest output
$0.03
per 1M tokens
Max context
5M
tokens
On-demand listed rates, OpenRouter routed quotes and Vercel reseller quotes. Enterprise commitments (committed-use discounts, provisioned throughput, negotiated rates) can be materially lower. An OpenRouter routed quote is the price of whichever upstream provider OpenRouter prefers today, so it moves day to day.
| Model ID | |||||
|---|---|---|---|---|---|
| InclusionAI: ling-2-6-flash | InclusionAI | 262K | $0.01Routed quote | $0.03Routed quote | inclusionai/ling-2.6-flash |
| DeepSeek Flash LatestPointer | DeepSeek | 1M | $0.013Routed quote | $0.891Routed quote | ~deepseek/deepseek-flash-latest |
| DeepSeek V4.1 Flash | DeepSeek | 1M | $0.013Routed quote | $0.891Routed quote | deepseek/deepseek-v4.1-flash |
| DeepSeek V4 Flash LatestPointer | DeepSeek | 1M | $0.0144Routed quote | $0.576Routed quote | ~deepseek/deepseek-v4-flash-latest |
| DeepSeek V4 Flash 0731 | DeepSeek | 1M | $0.016Routed quote | $0.64Routed quote | deepseek/deepseek-v4-flash-0731 |
| Granite 4.0 Micro | IBM | 131K | $0.017Routed quote | $0.112Routed quote | ibm-granite/granite-4.0-h-micro |
| gpt-oss-20b | OpenAI | 131K | $0.018Routed quote | $0.09Routed quote | openai/gpt-oss-20b |
| inclusionAI: Ling 3.0 Flash | InclusionAI | 262K | $0.021Routed quote | $0.063Routed quote | inclusionai/ling-3.0-flash |
| Nex-N2-Mini | Other | 262K | $0.025Routed quote | $0.10Routed quote | nex-agi/nex-n2-mini |
| Nex-N2.5-Mini | Other | 262K | $0.025Routed quote | $0.10Routed quote | nex-agi/nex-n2.5-mini |
| Llama 3.2 1B Instruct | Meta | 131K | $0.027Routed quote | $0.201Routed quote | meta-llama/llama-3.2-1b-instruct |
| Mistral Nemo | Mistral | 131K | $0.029Routed quote | $0.03Routed quote | mistralai/mistral-nemo |
| Qwen3.7 Flash | Alibaba | 1M | $0.03Routed quote | $0.13Routed quote | qwen/qwen3.7-flash |
| Schematron V2 Turbo | Other | 128K | $0.03Routed quote | $0.15Routed quote | inference-net/schematron-v2-turbo |
| Nova Micro 1.0 | Amazon | 128K | $0.035Routed quote | $0.14Routed quote | amazon/nova-micro-v1 |
| GLM Flash LatestPointer | Zhipu | 1M | $0.036Routed quote | $0.90Routed quote | ~z-ai/glm-flash-latest |
| gpt-oss-120b | OpenAI | 131K | $0.037Routed quote | $0.17Routed quote | openai/gpt-oss-120b |
| Command R7B (12-2024) | Cohere | 128K | $0.0375Routed quote | $0.15Routed quote | cohere/command-r7b-12-2024 |
| Extract | Other | 1M | $0.04Routed quote | n/aRouted quote | scaledown/extract |
| Mercury 2.5 | Inception | 260K | $0.04Routed quote | $0.15Routed quote | inception/mercury-2.5 |
| Mercury 2.5 Preview | Inception | 260K | $0.04Routed quote | $0.15Routed quote | inception/mercury-2.5-preview |
| Qwen3.8 27B | Alibaba | 262K | $0.04Routed quote | $2.30Routed quote | qwen/qwen3.8-27b |
| Sao10K: Llama 3 8B Lunaris | Sao10K | 8K | $0.04Routed quote | $0.05Routed quote | sao10k/l3-lunaris-8b |
| Summarize | Other | 1M | $0.04Routed quote | n/aRouted quote | scaledown/summarize |
| inclusionAI: Ling 3.0 Flash Fin | InclusionAI | 262K | $0.042Routed quote | $0.123Routed quote | inclusionai/ling-3.0-flash-fin |
| inclusionAI: Ling 3.0 Flash Sante | InclusionAI | 262K | $0.042Routed quote | $0.123Routed quote | inclusionai/ling-3.0-flash-sante |
| Hy-MT2-1.8B | Other | 8K | $0.044Routed quote | $0.177Routed quote | tencent/hy-mt2-1.8b |
| Gemma 3 12B | 131K | $0.05Routed quote | $0.15Routed quote | google/gemma-3-12b-it | |
| Gemma 3 4B | 131K | $0.05Routed quote | $0.10Routed quote | google/gemma-3-4b-it | |
| GLM 5.2 | Zhipu | 1M | $0.05Routed quote | $7.00Routed quote | z-ai/glm-5.2 |
| GPT-5 Nano | OpenAI | 5M | $0.05Routed quote | $0.40Routed quote | openai/gpt-5-nano |
| Granite 4.1 8B | IBM | 131K | $0.05Routed quote | $0.10Routed quote | ibm-granite/granite-4.1-8b |
| LFM2.5-24B-A2B | Liquid AI | 128K | $0.05Routed quote | $0.70Routed quote | liquid/lfm-2.5-24b-a2b |
| Llama 3.1 8B Instruct | Meta | 200K | $0.05Routed quote | $0.08Routed quote | meta-llama/llama-3.1-8b-instruct |
| Llama 3.2 3B Instruct | Meta | 131K | $0.05Routed quote | $0.33Routed quote | meta-llama/llama-3.2-3b-instruct |
| Mistral Small 3 | Mistral | 33K | $0.05Routed quote | $0.08Routed quote | mistralai/mistral-small-24b-instruct-2501 |
| Schematron V2 Small | Other | 128K | $0.05Routed quote | $0.23Routed quote | inference-net/schematron-v2-small |
| Solar Mini 4 | Other | 524K | $0.05Routed quote | $0.20Routed quote | upstage/solar-mini4 |
| Gemma 3n E4b It | 33K | $0.06Routed quote | $0.12Routed quote | google/gemma-3n-e4b-it | |
| Granite 4.2 8B | IBM | 131K | $0.06Routed quote | $0.25Routed quote | ibm-granite/granite-4.2-8b |
| inclusionAI: Ling 3.0 Flash VL | InclusionAI | 131K | $0.06Routed quote | $0.18Routed quote | inclusionai/ling-3.0-flash-vl |
| Laguna XS 2.1 | Poolside | 262K | $0.06Routed quote | $0.12Routed quote | poolside/laguna-xs-2.1 |
| Nemotron 3 Nano 30B A3B | NVIDIA | 262K | $0.06Routed quote | $0.24Routed quote | nvidia/nemotron-3-nano-30b-a3b |
| Nova Lite 1.0 | Amazon | 300K | $0.06Routed quote | $0.24Routed quote | amazon/nova-lite-v1 |
| GLM 4.7 Flash | Zhipu | 203K | $0.0605Routed quote | $0.40Routed quote | z-ai/glm-4.7-flash |
| GLM LatestPointer | Zhipu | 1M | $0.063Routed quote | $4.40Routed quote | ~z-ai/glm-latest |
| Qwen3.5-Flash | Alibaba | 1M | $0.065Routed quote | $0.26Routed quote | qwen/qwen3.5-flash-02-23 |
| Nemotron 3.5 Lightning | NVIDIA | 1M | $0.07Routed quote | $0.20Routed quote | nvidia/nemotron-3.5-lightning |
| Phi 4 | Microsoft | 16K | $0.07Routed quote | $0.14Routed quote | microsoft/phi-4 |
| Qwen3 Coder 30B A3B Instruct | Alibaba | 262K | $0.07Routed quote | $0.28Routed quote | qwen/qwen3-coder-30b-a3b-instruct |
1–50 of 440
Page 1 of 9
Listed prices from LiteLLM, OpenRouter and Vercel · catalogue refreshed Oct 14, 2026 · 110 prices older, back to Jul 19, 2026
Every weekday
AI moves fast. Here's your debrief.
News, analysis, tools, and more.
For people who build with AI